Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 23392
    Prev
    Next
    INDEX
    Explanations

    elements related to age and education metrics in datasets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uve
    -0.17
    pNet
    -0.17
     ?><?
    -0.16
    ebin
    -0.15
    benh
    -0.15
    EDIA
    -0.14
    removeAttr
    -0.14
    Ĥ¹
    -0.14
    Ìĥ
    -0.14
    ILD
    -0.14
    POSITIVE LOGITS
    =
    0.23
     
    0.20
     ÑģÑĤановиÑĤÑĮ
    0.15
    inois
    0.14
    }=
    0.14
    ework
    0.14
     ÑģоÑģÑĤавлÑıеÑĤ
    0.14
    uj
    0.14
    ilis
    0.13
    115
    0.13
    Activations Density 0.112%

    No Known Activations